© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 51011
    Prev
    Next
    INDEX
    Explanations

    referencing biblical books and verses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    锉
    0.57
     экологи
    0.49
    ༻
    0.49
    压缩
    0.47
    iciencies
    0.46
    INOIS
    0.46
    㗊
    0.46
    cheduled
    0.45
     રહી
    0.45
     Oldborough
    0.45
    POSITIVE LOGITS
     usages
    0.56
     usage
    0.52
     kde
    0.52
     usos
    0.47
     terminology
    0.46
     robbing
    0.46
     W
    0.46
     cf
    0.46
     mentions
    0.45
     mention
    0.45
    Activations Density 0.022%

    No Known Activations